AgentScout / Tasks / Testing apps / Testing and QA

AI testing and QA tools

Agents that write and run tests and report what breaks. Of the 26 tools on our testing apps page, 10 fit this narrower job. By pricing: 3 open source, 1 free or freemium, 5 paid, usage-based or enterprise, 1 pricing on the maker's site. The most-starred open repos here are Midscene.js (15,311 stars), Shippie (2,510 stars), Hercules (1,190 stars). Most come from the coding (5), evals & observability (3), browser/computer use (1) categories.

Updated

Midscene.js logo

Midscene.js

Newbrowser/computer useOpen source

Vision-driven UI automation and E2E testing framework where a GUI agent carries out natural-language steps on web, mobile and desktop apps.

Added

Shippie logo

Shippie

NewcodingOpen source

Extendable code review and QA agent that reads your diff, explores the codebase and posts focused review comments.

Added

Hercules logo

Hercules

NewcodingOpen source

Open-source testing agent that turns plain Gherkin steps into end-to-end UI, API, accessibility and security tests.

Added

agent-qa (Vostride) logo

agent-qa (Vostride)

Newevals & observabilitySee site

A self-improving AI QA agent with persistent memory that tests web, Android and iOS apps from plain-English test steps, for developers and coding agents.

Added

Encord Agents logo

Encord Agents

NewvisionPaid

Encord's agents that plug foundation models or your own models into labeling workflows to pre-label, segment, track, route and QA image, video and multimodal data, with a no-code catalog and an open-source SDK.

Added

CoTester logo

CoTester

NewcodingPaid

TestGrid's AI software testing agent that creates, runs and maintains self-healing tests for enterprise apps.

Added

Coval logo

Coval

Newevals & observabilityPaid

Testing and evaluation platform for voice agents, with simulations, production evals and human QA.

Added

Hamming AI logo

Hamming AI

evals & observabilityPaid

Testing and QA platform for voice and chat agents that generates scenarios and replays real calls.

Added

KaneAI logo

KaneAI

codingPaid

AI testing agent that plans, writes and evolves end-to-end tests from natural language.

Added

Momentic logo

Momentic

NewcodingFreemium

AI testing platform with an AI QA agent that runs and maintains plain-English tests and reports bugs with repro steps.

Added

GitHub repos (5)

RepoGitHub starsLicenceLast push
Midscene.js ↗15,311MIT2026-10-21
Shippie ↗2,510—2026-07-02
Hercules ↗1,190—2026-10-14
agent-qa (Vostride) ↗912—2026-08-03
Encord Agents ↗18Apache License 2.02026-09-23

5 repos. Stars and licence come from each repo, checked when the listing was last verified.

FAQ

What are the best AI tools for testing apps focused on testing and QA?

We list 10. The first three by GitHub stars and featured status are Midscene.js: Vision-driven UI automation and E2E testing framework where a GUI agent carries out natural-language steps on web, mobile and desktop apps.; Shippie: Extendable code review and QA agent that reads your diff, explores the codebase and posts focused review comments.; Hercules: Open-source testing agent that turns plain Gherkin steps into end-to-end UI, API, accessibility and security tests.

Are there free or open-source options?

Yes: 3 open source, 1 free or freemium, 5 paid, usage-based or enterprise, 1 pricing on the maker's site. Pricing is as each maker states it.

More from testing apps

Tools are grouped by what each says it does. Missing one? Submit it free.

Get the best new AI agents, weekly

One short email with new tools, launches and what's worth trying. Free, unsubscribe anytime.